{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:ADWAIHYQTOVMFW63AFKRSBWJNC","short_pith_number":"pith:ADWAIHYQ","canonical_record":{"source":{"id":"1708.08311","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-28T13:51:09Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"321513a72152bbb78edbca6cb0e624c4a26cb1864d32a8ca4db5a704503f2f10","abstract_canon_sha256":"3475c7a30ee80e447cc031d8bd196252061b98d834ff0d6c96c17bcd26c4f1f2"},"schema_version":"1.0"},"canonical_sha256":"00ec041f109baac2dbdb01551906c9689a8c8f5e3a64919ee9e621df684e55f2","source":{"kind":"arxiv","id":"1708.08311","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.08311","created_at":"2026-05-18T00:36:36Z"},{"alias_kind":"arxiv_version","alias_value":"1708.08311v1","created_at":"2026-05-18T00:36:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.08311","created_at":"2026-05-18T00:36:36Z"},{"alias_kind":"pith_short_12","alias_value":"ADWAIHYQTOVM","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"ADWAIHYQTOVMFW63","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"ADWAIHYQ","created_at":"2026-05-18T12:31:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:ADWAIHYQTOVMFW63AFKRSBWJNC","target":"record","payload":{"canonical_record":{"source":{"id":"1708.08311","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-28T13:51:09Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"321513a72152bbb78edbca6cb0e624c4a26cb1864d32a8ca4db5a704503f2f10","abstract_canon_sha256":"3475c7a30ee80e447cc031d8bd196252061b98d834ff0d6c96c17bcd26c4f1f2"},"schema_version":"1.0"},"canonical_sha256":"00ec041f109baac2dbdb01551906c9689a8c8f5e3a64919ee9e621df684e55f2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:36.399189Z","signature_b64":"R+croUQTNFoft3ojPgmXdFB7smP9TmjJt+1Rs2P+UOJUBkvWS8b/CJdF4/kvAjLApu0I3D1lQDK07ahQadGxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00ec041f109baac2dbdb01551906c9689a8c8f5e3a64919ee9e621df684e55f2","last_reissued_at":"2026-05-18T00:36:36.398557Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:36.398557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.08311","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:36:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yu3lr58BWuZJhZvn6KZ3n88k5d/n85dm8A9rPTyxf+GX3RPSH9yNOZryb9BLu2aUgBEbKJG8W5AuEKrlAjWUBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T13:22:22.828149Z"},"content_sha256":"16caa1f5cd7bbe04dcce0328bc688358c2510daa73ae904338282ab17d342643","schema_version":"1.0","event_id":"sha256:16caa1f5cd7bbe04dcce0328bc688358c2510daa73ae904338282ab17d342643"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:ADWAIHYQTOVMFW63AFKRSBWJNC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Learning Sparse Ternary Projections for Compressed Sensing of Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Duc Minh Nguyen, Evaggelia Tsiligianni, Nikos Deligiannis","submitted_at":"2017-08-28T13:51:09Z","abstract_excerpt":"Compressed sensing (CS) is a sampling theory that allows reconstruction of sparse (or compressible) signals from an incomplete number of measurements, using of a sensing mechanism implemented by an appropriate projection matrix. The CS theory is based on random Gaussian projection matrices, which satisfy recovery guarantees with high probability; however, sparse ternary {0, -1, +1} projections are more suitable for hardware implementation. In this paper, we present a deep learning approach to obtain very sparse ternary projections for compressed sensing. Our deep learning architecture jointly "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.08311","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:36:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9mf3h3GjEnIKvjrnPQAGAxBaX3e2rnu7cs1V7MjNpbxls+5bNGCfApfXhHhORMl4GzzA9mz4YsHJogVcwELhDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T13:22:22.828515Z"},"content_sha256":"d36de01a3cca2b947df9891e3b23c99c397f18167556bce0b59413a5d8daea35","schema_version":"1.0","event_id":"sha256:d36de01a3cca2b947df9891e3b23c99c397f18167556bce0b59413a5d8daea35"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ADWAIHYQTOVMFW63AFKRSBWJNC/bundle.json","state_url":"https://pith.science/pith/ADWAIHYQTOVMFW63AFKRSBWJNC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ADWAIHYQTOVMFW63AFKRSBWJNC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-11T13:22:22Z","links":{"resolver":"https://pith.science/pith/ADWAIHYQTOVMFW63AFKRSBWJNC","bundle":"https://pith.science/pith/ADWAIHYQTOVMFW63AFKRSBWJNC/bundle.json","state":"https://pith.science/pith/ADWAIHYQTOVMFW63AFKRSBWJNC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ADWAIHYQTOVMFW63AFKRSBWJNC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:ADWAIHYQTOVMFW63AFKRSBWJNC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3475c7a30ee80e447cc031d8bd196252061b98d834ff0d6c96c17bcd26c4f1f2","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-28T13:51:09Z","title_canon_sha256":"321513a72152bbb78edbca6cb0e624c4a26cb1864d32a8ca4db5a704503f2f10"},"schema_version":"1.0","source":{"id":"1708.08311","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.08311","created_at":"2026-05-18T00:36:36Z"},{"alias_kind":"arxiv_version","alias_value":"1708.08311v1","created_at":"2026-05-18T00:36:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.08311","created_at":"2026-05-18T00:36:36Z"},{"alias_kind":"pith_short_12","alias_value":"ADWAIHYQTOVM","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"ADWAIHYQTOVMFW63","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"ADWAIHYQ","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:d36de01a3cca2b947df9891e3b23c99c397f18167556bce0b59413a5d8daea35","target":"graph","created_at":"2026-05-18T00:36:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Compressed sensing (CS) is a sampling theory that allows reconstruction of sparse (or compressible) signals from an incomplete number of measurements, using of a sensing mechanism implemented by an appropriate projection matrix. The CS theory is based on random Gaussian projection matrices, which satisfy recovery guarantees with high probability; however, sparse ternary {0, -1, +1} projections are more suitable for hardware implementation. In this paper, we present a deep learning approach to obtain very sparse ternary projections for compressed sensing. Our deep learning architecture jointly ","authors_text":"Duc Minh Nguyen, Evaggelia Tsiligianni, Nikos Deligiannis","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-28T13:51:09Z","title":"Deep Learning Sparse Ternary Projections for Compressed Sensing of Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.08311","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:16caa1f5cd7bbe04dcce0328bc688358c2510daa73ae904338282ab17d342643","target":"record","created_at":"2026-05-18T00:36:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3475c7a30ee80e447cc031d8bd196252061b98d834ff0d6c96c17bcd26c4f1f2","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-28T13:51:09Z","title_canon_sha256":"321513a72152bbb78edbca6cb0e624c4a26cb1864d32a8ca4db5a704503f2f10"},"schema_version":"1.0","source":{"id":"1708.08311","kind":"arxiv","version":1}},"canonical_sha256":"00ec041f109baac2dbdb01551906c9689a8c8f5e3a64919ee9e621df684e55f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00ec041f109baac2dbdb01551906c9689a8c8f5e3a64919ee9e621df684e55f2","first_computed_at":"2026-05-18T00:36:36.398557Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:36:36.398557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R+croUQTNFoft3ojPgmXdFB7smP9TmjJt+1Rs2P+UOJUBkvWS8b/CJdF4/kvAjLApu0I3D1lQDK07ahQadGxBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:36:36.399189Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.08311","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16caa1f5cd7bbe04dcce0328bc688358c2510daa73ae904338282ab17d342643","sha256:d36de01a3cca2b947df9891e3b23c99c397f18167556bce0b59413a5d8daea35"],"state_sha256":"4d2356e72fe4fb5e63f1f863e10a5e9fa7ca87a94de1838248b4054c1fffccd6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k8+Hys9i60S+4+o/4F6Eq/c2NQUnpfQFvqAh6kcWmcif5lchkPN8tDXl6kmRFiUJPlCRpwJN7VKV6IbY/JBECg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T13:22:22.830787Z","bundle_sha256":"73be3fba415f371b95cfc9c28d3863033e04204e26284e1eff1db3b8d68ff0e9"}}